start_session

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so richly: it discloses process spawning, TCP server injection via -source, port 9999 probing, session reuse behavior, and the warning that omitting port will attach to the same GUI rather than create a new one. This is exactly the kind of non-obvious behavioral context agents need.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a mode list and an Args block, and every major section adds value. It is lengthy and dense, especially the port semantics (including the 'B 方案' reference), which makes it slightly heavier than ideal for quick consumption, but it remains organized and useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with 5 parameters, no annotations, and no per-parameter schema descriptions, yet the description covers modes, session lifecycle, port probing, custom path, and timeout. An output schema exists, so return-value details are unnecessary. The description is complete enough for correct tool invocation without any external documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does: the Args block explains session_id, mode, port, vivado_path, and timeout, and adds critical port semantics including port=0 for allocating a fresh instance. This fully replaces what would normally be in parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with '启动一个新的 Vivado 会话' (start a new Vivado session), stating a clear verb and resource. It distinguishes itself from siblings like stop_session and list_sessions by focusing on the launch/creation aspect, and further clarifies the three operating modes (gui, tcl, attach).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is explicit for choosing modes: 'tcl' for headless CI/batch, 'attach' for connecting to an existing GUI, and 'gui' as the default. Port semantics for multi-instance vs reuse are also spelled out in detail. It lacks explicit 'do not use' exclusions, but the alternatives are clearly delineated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.